Javier Ruiz Hidalgo


Javier Ruiz Hidalgo received a degree in Telecommunications Engineering at the Universitat Politècnica de Catalunya (UPC), Barcelona, Spain in 1997. From 1998 to 1999, he developed an MSc by Research on the field of Computer Vision by the University of East Anglia (UEA) in Norwich, UK. During 1999 he joined the Image Processing Group at UPC working on image and video indexing in the context of the MPEG-7 standard. In 2006, he received his PhD. in the field of image processing.

Since 1999 he has been involved in various European Projects as a researcher from the Image Processing Group at UPC. During 1999 and 2000 he worked in the ACTS(AC308) DICEMAN project developing new descriptors and representations for image and video sequences. Since 2001 he is also involved in the IST/FET(2000-26467) project MASCOT developing an efficient compression scheme exploiting metadata information. In 2009 he worked as principal researcher for the national project HESPERIA involved in improving the security of large infrastructures such as airports and power plants. From 2010 to 2013 he was principal researcher for the EU project FASCINATE working on interactive human computer interfaces using 3D data.

Since 2001 he is an Associate Professor at the Universitat Politècnica de Catalunya. He is currently lecturing on the area of digital signal and systems and image processing. His current research interests include 3D video coding, 3D analysis and super-resolution.

Conference Papers top

D. Bazazian, Casas, J., and Ruiz-Hidalgo, J., Segmentation-based Multi-Scale Edge Extraction to Measure the Persistence of Features in Unorganized Point Clouds, in International Conference on Computer Vision Theory and Applications, Porto, Portugal, 2017. (4.3 MB)
B. Luque, Morros, J. R., and Ruiz-Hidalgo, J., Spatio-Temporal Road Detection from Aerial Imagery using CNNs, in International Conference on Computer Vision Theory and Applications, Porto, Portugal, 2017. (6.14 MB)
D. van Sabben, Ruiz-Hidalgo, J., Suau, X., and Casas, J., Collaborative voting of 3D features for robust gesture estimation, in International Conference on Acoustics, Speech and Signal Processing, New Orleans, USA, 2017. (605.86 KB)
A. Pujol-Miró, Ruiz-Hidalgo, J., and Casas, J., Registration of Images to Unorganized 3D Point Clouds Using Contour Cues, in The 25th European Signal Processing Conference (EUSIPCO 2017), Kos island, Greece, 2017. (3.14 MB)
E. Perez-Pellitero, Salvador, J., Ruiz-Hidalgo, J., and Rosenhahn, B., Half Hypersphere Confinement for Piecewise Linear Regression, in IEEE Winter Conference on Applications of Computer Vision, Lake Placid, NY, USA, 2016. (7.01 MB)

Theses top

E. Perez-Pellitero, Manifold Learning for Super Resolution, Leibniz Universität Hannover, Hannover, 2017. (18.6 MB)
M. Maceira, Multi-view depth coding based on a region representation combining color and depth information, Universitat Politècnica de Catalunya (UPC), 2017.
X. Suau, Human body analysis using depth data, Universitat Politècnica de Catalunya (UPC), 2013. (10.67 MB)
J. Ruiz-Hidalgo, On the Synergy between indexing and compression representations for video sequences, Universitat Politècnica de Catalunya (UPC), 2006. (4.35 MB)

Research Areas top

Region-based image and video processing Internal Jan
Multiview Coding Internal Jul
Multi-view/Multi-sensor scene capture, analysis and representation Internal Mar